課程信息
50,879 次近期查看

第 3 門課程(共 4 門)

100% 在線

立即開始,按照自己的計劃學習。

可靈活調整截止日期

根據您的日程表重置截止日期。

中級

Probabilities & Expectations, basic linear algebra, basic calculus, Python 3.0 (at least 1 year), implementing algorithms from pseudocode.

完成時間大約為17 小時

建議:4-6 hours/week...

英語(English)

字幕:英語(English)

您將獲得的技能

Artificial Intelligence (AI)Machine LearningReinforcement LearningFunction ApproximationIntelligent Systems

第 3 門課程(共 4 門)

100% 在線

立即開始,按照自己的計劃學習。

可靈活調整截止日期

根據您的日程表重置截止日期。

中級

Probabilities & Expectations, basic linear algebra, basic calculus, Python 3.0 (at least 1 year), implementing algorithms from pseudocode.

完成時間大約為17 小時

建議:4-6 hours/week...

英語(English)

字幕:英語(English)

學習Course的學生是

  • Data Scientists
  • Scientists
  • Machine Learning Engineers
  • Researchers
  • Financial Analysts

教學大綱 - 您將從這門課程中學到什麼

1
完成時間為 1 小時

Welcome to the Course!

2 個視頻 (總計 12 分鐘), 2 個閱讀材料
2 個視頻
Meet your instructors!8分鐘
2 個閱讀材料
Read Me: Pre-requisites and Learning Objectives10分鐘
Reinforcement Learning Textbook10分鐘
完成時間為 6 小時

On-policy Prediction with Approximation

13 個視頻 (總計 69 分鐘), 1 個閱讀材料, 2 個測驗
13 個視頻
Generalization and Discrimination5分鐘
Framing Value Estimation as Supervised Learning3分鐘
The Value Error Objective4分鐘
Introducing Gradient Descent7分鐘
Gradient Monte for Policy Evaluation5分鐘
State Aggregation with Monte Carlo7分鐘
Semi-Gradient TD for Policy Evaluation3分鐘
Comparing TD and Monte Carlo with State Aggregation4分鐘
Doina Precup: Building Knowledge for AI Agents with Reinforcement Learning7分鐘
The Linear TD Update3分鐘
The True Objective for TD5分鐘
Week 1 Summary4分鐘
1 個閱讀材料
Weekly Reading: On-policy Prediction with Approximation40分鐘
1 個練習
On-policy Prediction with Approximation30分鐘
2
完成時間為 8 小時

Constructing Features for Prediction

11 個視頻 (總計 52 分鐘), 1 個閱讀材料, 2 個測驗
11 個視頻
Generalization Properties of Coarse Coding5分鐘
Tile Coding3分鐘
Using Tile Coding in TD4分鐘
What is a Neural Network?3分鐘
Non-linear Approximation with Neural Networks4分鐘
Deep Neural Networks3分鐘
Gradient Descent for Training Neural Networks8分鐘
Optimization Strategies for NNs4分鐘
David Silver on Deep Learning + RL = AI?9分鐘
Week 2 Review2分鐘
1 個閱讀材料
Weekly Reading: On-policy Prediction with Approximation II40分鐘
1 個練習
Constructing Features for Prediction28分鐘
3
完成時間為 8 小時

Control with Approximation

7 個視頻 (總計 41 分鐘), 1 個閱讀材料, 2 個測驗
7 個視頻
Episodic Sarsa in Mountain Car5分鐘
Expected Sarsa with Function Approximation2分鐘
Exploration under Function Approximation3分鐘
Average Reward: A New Way of Formulating Control Problems10分鐘
Satinder Singh on Intrinsic Rewards12分鐘
Week 3 Review2分鐘
1 個閱讀材料
Weekly Reading: On-policy Control with Approximation40分鐘
1 個練習
Control with Approximation40分鐘
4
完成時間為 6 小時

Policy Gradient

11 個視頻 (總計 55 分鐘), 1 個閱讀材料, 2 個測驗
11 個視頻
Advantages of Policy Parameterization5分鐘
The Objective for Learning Policies5分鐘
The Policy Gradient Theorem5分鐘
Estimating the Policy Gradient4分鐘
Actor-Critic Algorithm5分鐘
Actor-Critic with Softmax Policies3分鐘
Demonstration with Actor-Critic6分鐘
Gaussian Policies for Continuous Actions7分鐘
Week 4 Summary3分鐘
Congratulations! Course 4 Preview2分鐘
1 個閱讀材料
Weekly Reading: Policy Gradient Methods40分鐘
1 個練習
Policy Gradient Methods45分鐘

講師

Avatar

Martha White

Assistant Professor
Computing Science
Avatar

Adam White

Assistant Professor
Computing Science

關於 阿尔伯塔大学

UAlberta is considered among the world’s leading public research- and teaching-intensive universities. As one of Canada’s top universities, we’re known for excellence across the humanities, sciences, creative arts, business, engineering and health sciences....

關於 Alberta Machine Intelligence Institute

The Alberta Machine Intelligence Institute (Amii) is home to some of the world’s top talent in machine intelligence. We’re an Alberta-based research institute that pushes the bounds of academic knowledge and guides business understanding of artificial intelligence and machine learning....

關於 强化学习 專項課程

The Reinforcement Learning Specialization consists of 4 courses exploring the power of adaptive learning systems and artificial intelligence (AI). Harnessing the full potential of artificial intelligence requires adaptive learning systems. Learn how Reinforcement Learning (RL) solutions help solve real-world problems through trial-and-error interaction by implementing a complete RL solution from beginning to end. By the end of this Specialization, learners will understand the foundations of much of modern probabilistic artificial intelligence (AI) and be prepared to take more advanced courses or to apply AI tools and ideas to real-world problems. This content will focus on “small-scale” problems in order to understand the foundations of Reinforcement Learning, as taught by world-renowned experts at the University of Alberta, Faculty of Science. The tools learned in this Specialization can be applied to game development (AI), customer interaction (how a website interacts with customers), smart assistants, recommender systems, supply chain, industrial control, finance, oil & gas pipelines, industrial control systems, and more....
强化学习

常見問題

  • 注册以便获得证书后,您将有权访问所有视频、测验和编程作业(如果适用)。只有在您的班次开课之后,才可以提交和审阅同学互评作业。如果您选择在不购买的情况下浏览课程,可能无法访问某些作业。

  • 您注册课程后,将有权访问专项课程中的所有课程,并且会在完成课程后获得证书。您的电子课程证书将添加到您的成就页中,您可以通过该页打印您的课程证书或将其添加到您的领英档案中。如果您只想阅读和查看课程内容,可以免费旁听课程。

還有其他問題嗎?請訪問 學生幫助中心